harsh814's picture
Update README.md
f63978f verified
|
raw
history blame
19.4 kB
metadata
tags:
  - feature-extraction
license: bsd-3-clause
library_name: transformers
duplicated_from: florentgbelidji/blip_image_embeddings
widget:
  - text: >-
      iVBORw0KGgoAAAANSUhEUgAAAEQAAABCCAYAAADuSnCvAAAMPWlDQ1BJQ0MgUHJvZmlsZQAASImVVwdYU8kanVuSkEBooUsJvQkiNYCUEFoA6V1UQhIglBgDQcWOLiq4drGADV0VUew0C4ooFhbF3hcLKsq6WLArb1JA133le/N9c++5Z/45f7lzywCgdoIjEuWh6gDkCwvFsSEB9OSUVDrpKcAAGQDgBGgcboGIGR0dAa/A0Pnv7d11gEjPVxykWv8c/69Ng8cv4AKAREOcwSvg5kN8CAC8iisSFwJAlPLmUwpFUgw70BLDACFeKMVZclwlxRlyvE9mEx/LgrgNACUVDkecBYDqJcjTi7hZUEO1X5qZkCcQAqBGh9g3P38SD+J0iG2gjQhiqT4j4wedrL9pZgxrcjhZw1iei6wpBQoKRHmcaf9nOf53y8+TDPmwgl0lWxwaK80Z1u1m7qRwKVaBuE+YERkFsSbEHwQ8mT3EKCVbEpogt0cNuQUsWDOgA7ETjxMYDrEhxMHCvMgIBZ+RKQhmQwxXCDpVUMiOh1gP4oX8gqA4hc1m8aRYhS+0PlPMYir4sxyxzK/U131JbgJTof86m89W6GOqxdnxSRBTILYoEiRGQqwKsWNBbly4wmZMcTYrcshGLImVxm8BcSxfGBIg18eKMsXBsQr7svyCoXyxzdkCdqQCHyjMjg+V1wdr43Jk8cNcsEt8ITNhSIdfkBwxlAuPHxgkzx17xhcmxCl0PogKA2Llc3GKKC9aYY+b8fNCpLwZxK4FRXGKuXhiIVyQcn08U1QYHS+PEy/O4YRFy+PBl4EIwAKBgA4ksGeASSAHCDr7GvrglXwkGHCAGGQBPnBQMEMzkmQjQniMA8XgT4j4oGB4XoBslA+KIP91mJUfHUCmbLRINiMXPIE4H4SDPHgtkc0SDntLBI8hI/iHdw7sXBhvHuzS8X/PD7HfGSZkIhSMZMgjXW3IkhhEDCSGEoOJtrgB7ot74xHw6A+7M87APYfy+G5PeELoIjwkXCN0E25NFJSIf4pyLOiG+sGKWmT8WAvcCmq64QG4D1SHyrgObgAccFfoh4n7Qc9ukGUp4pZWhf6T9t8y+OFuKOzITmSUrEv2J9v8PFPVTtVtWEVa6x/rI481Y7jerOGRn/2zfqg+D57Df7bEFmIHsXbsJHYOO4o1ADrWgjViHdgxKR5eXY9lq2vIW6wsnlyoI/iHv6E7K61kgVOtU6/TF/lYIX+q9B0NWJNE08SCrOxCOhN+Efh0tpDrOJLu7OTsAoD0+yJ/fb2JkX03EJ2O79y8PwDwaRkcHDzynQtrAWC/B3z8m75zNgz46VAG4GwTVyIuknO49ECAbwk1+KTpA2NgDmxgPs7AHXgDfxAEwkAUiAcpYAKMPhuuczGYAmaAuaAUlINlYDVYDzaBrWAn2AMOgAZwFJwEZ8AFcAlcA3fg6ukBL0A/eAc+IwhCQqgIDdFHTBBLxB5xRhiILxKERCCxSAqSjmQhQkSCzEDmIeXICmQ9sgWpQfYjTchJ5BzShdxCHiC9yGvkE4qhKqgWaoRaoaNQBspEw9F4dDyahU5Gi9H56BJ0LVqN7kbr0ZPoBfQa2o2+QAcwgCljOpgp5oAxMBYWhaVimZgYm4WVYRVYNVaHNcP7fAXrxvqwjzgRp+F03AGu4FA8Aefik/FZ+GJ8Pb4Tr8fb8Cv4A7wf/0agEgwJ9gQvApuQTMgiTCGUEioI2wmHCafhs9RDeEckEnWI1kQP+CymEHOI04mLiRuIe4kniF3ER8QBEomkT7In+ZCiSBxSIamUtI60m9RCukzqIX1QUlYyUXJWClZKVRIqlShVKO1SOq50Wemp0meyOtmS7EWOIvPI08hLydvIzeSL5B7yZ4oGxZriQ4mn5FDmUtZS6iinKXcpb5SVlc2UPZVjlAXKc5TXKu9TPqv8QPmjiqaKnQpLJU1ForJEZYfKCZVbKm+oVKoV1Z+aSi2kLqHWUE9R71M/qNJUHVXZqjzV2aqVqvWql1VfqpHVLNWYahPUitUq1A6qXVTrUyerW6mz1Dnqs9Qr1ZvUb6gPaNA0RmtEaeRrLNbYpXFO45kmSdNKM0iTpzlfc6vmKc1HNIxmTmPRuLR5tG2007QeLaKWtRZbK0erXGuPVqdWv7amtqt2ovZU7UrtY9rdOpiOlQ5bJ09nqc4Bnes6n3SNdJm6fN1FunW6l3Xf643Q89fj65Xp7dW7pvdJn64fpJ+rv1y/Qf+eAW5gZxBjMMVgo8Fpg74RWiO8R3BHlI04MOK2IWpoZxhrON1wq2GH4YCRsVGIkchondEpoz5jHWN/4xzjVcbHjXtNaCa+JgKTVSYtJs/p2nQmPY++lt5G7zc1NA01lZhuMe00/WxmbZZgVmK21+yeOcWcYZ5pvsq81bzfwsRirMUMi1qL25ZkS4ZltuUay3bL91bWVklWC6warJ5Z61mzrYuta63v2lBt/Gwm21TbXLUl2jJsc2032F6yQ+3c7LLtKu0u2qP27vYC+w32XSMJIz1HCkdWj7zhoOLAdChyqHV44KjjGOFY4tjg+HKUxajUUctHtY/65uTmlOe0zenOaM3RYaNLRjePfu1s58x1rnS+6kJ1CXaZ7dLo8srV3pXvutH1phvNbazbArdWt6/uHu5i9zr3Xg8Lj3SPKo8bDC1GNGMx46wnwTPAc7bnUc+PXu5ehV4HvP7ydvDO9d7l/WyM9Rj+mG1jHvmY+XB8tvh0+9J90303+3b7mfpx/Kr9Hvqb+/P8t/s/Zdoyc5i7mS8DnALEAYcD3rO8WDNZJwKxwJDAssDOIM2ghKD1QfeDzYKzgmuD+0PcQqaHnAglhIaHLg+9wTZic9k17P4wj7CZYW3hKuFx4evDH0bYRYgjmseiY8PGrhx7N9IyUhjZEAWi2FEro+5FW0dPjj4SQ4yJjqmMeRI7OnZGbHscLW5i3K64d/EB8Uvj7yTYJEgSWhPVEtMSaxLfJwUmrUjqTh6VPDP5QopBiiClMZWUmpi6PXVgXNC41eN60tzSStOuj7ceP3X8uQkGE/ImHJuoNpEz8WA6IT0pfVf6F04Up5ozkMHOqMro57K4a7gveP68Vbxevg9/Bf9ppk/misxnWT5ZK7N6s/2yK7L7BCzBesGrnNCcTTnvc6Nyd+QO5iXl7c1Xyk/PbxJqCnOFbZOMJ02d1CWyF5WKuid7TV49uV8cLt5egBSML2gs1II/8h0SG8kvkgdFvkWVRR+mJE45OFVjqnBqxzS7aYumPS0OLv5tOj6dO711humMuTMezGTO3DILmZUxq3W2+ez5s3vmhMzZOZcyN3fu7yVOJStK3s5Lmtc832j+nPmPfgn5pbZUtVRcemOB94JNC/GFgoWdi1wWrVv0rYxXdr7cqbyi/Mti7uLzv47+de2vg0syl3QudV+6cRlxmXDZ9eV+y3eu0FhRvOLRyrEr61fRV5Wtert64upzFa4Vm9ZQ1kjWdK+NWNu4zmLdsnVf1mevv1YZULm3yrBqUdX7DbwNlzf6b6zbZLSpfNOnzYLNN7eEbKmvtqqu2ErcWrT1ybbEbe2/MX6r2W6wvXz71x3CHd07Y3e21XjU1Owy3LW0Fq2V1PbuTtt9aU/gnsY6h7ote3X2lu8D+yT7nu9P33/9QPiB1oOMg3WHLA9VHaYdLqtH6qfV9zdkN3Q3pjR2NYU1tTZ7Nx8+4nhkx1HTo5XHtI8tPU45Pv/4YEtxy8AJ0Ym+k1knH7VObL1zKvnU1baYts7T4afPngk+c6qd2d5y1ufs0XNe55rOM843XHC/UN/h1nH4d7ffD3e6d9Zf9LjYeMnzUnPXmK7jl/0un7wSeOXMVfbVC9cir3VdT7h+80baje6bvJvPbuXdenW76PbnO3PuEu6W3VO/V3Hf8H71H7Z/7O127z72IPBBx8O4h3cecR+9eFzw+EvP/CfUJxVPTZ7WPHN+drQ3uPfS83HPe16IXnzuK/1T48+qlzYvD/3l/1dHf3J/zyvxq8HXi9/ov9nx1vVt60D0wP13+e8+vy/7oP9h50fGx/ZPSZ+efp7yhfRl7Vfbr83fwr/dHcwfHBRxxBzZrwAGO5qZCcDrHQBQUwCgwf0ZZZx8/ydriHzPKkPgP2H5HlHW3AGog//vMX3w7+YGAPu2we0X1FdLAyCaCkC8J0BdXIb70F5Ntq+UNiLcB2yO/JqRnwH+TZPvOX+I++czkKq6gp/P/wJFeHxXZUgo9wAAAIplWElmTU0AKgAAAAgABAEaAAUAAAABAAAAPgEbAAUAAAABAAAARgEoAAMAAAABAAIAAIdpAAQAAAABAAAATgAAAAAAAACQAAAAAQAAAJAAAAABAAOShgAHAAAAEgAAAHigAgAEAAAAAQAAAESgAwAEAAAAAQAAAEIAAAAAQVNDSUkAAABTY3JlZW5zaG90WTBWpAAAAAlwSFlzAAAWJQAAFiUBSVIk8AAAAdRpVFh0WE1MOmNvbS5hZG9iZS54bXAAAAAAADx4OnhtcG1ldGEgeG1sbnM6eD0iYWRvYmU6bnM6bWV0YS8iIHg6eG1wdGs9IlhNUCBDb3JlIDYuMC4wIj4KICAgPHJkZjpSREYgeG1sbnM6cmRmPSJodHRwOi8vd3d3LnczLm9yZy8xOTk5LzAyLzIyLXJkZi1zeW50YXgtbnMjIj4KICAgICAgPHJkZjpEZXNjcmlwdGlvbiByZGY6YWJvdXQ9IiIKICAgICAgICAgICAgeG1sbnM6ZXhpZj0iaHR0cDovL25zLmFkb2JlLmNvbS9leGlmLzEuMC8iPgogICAgICAgICA8ZXhpZjpQaXhlbFlEaW1lbnNpb24+NjY8L2V4aWY6UGl4ZWxZRGltZW5zaW9uPgogICAgICAgICA8ZXhpZjpQaXhlbFhEaW1lbnNpb24+Njg8L2V4aWY6UGl4ZWxYRGltZW5zaW9uPgogICAgICAgICA8ZXhpZjpVc2VyQ29tbWVudD5TY3JlZW5zaG90PC9leGlmOlVzZXJDb21tZW50PgogICAgICA8L3JkZjpEZXNjcmlwdGlvbj4KICAgPC9yZGY6UkRGPgo8L3g6eG1wbWV0YT4KS74hmQAAABxpRE9UAAAAAgAAAAAAAAAhAAAAKAAAACEAAAAhAAARS0n0ZfAAABEXSURBVHgBRNp7k1zVdQXw0495PzUjIZHC4KTs4gPwWYwxEYoCMZgY28Q439FJJZXCqYKyKfMHREJCjxmN5tEz0z2d9dtnGl9VMzP3nnvO3muvvfY+pxn85rcfzS8uzltrgzafX7XxeNyWlpbbdHrZLi8v28rKStvY2Kjnw+GgTSbn7ezs9Ie/r+bzNhqN2tlkkvEXbW1tvY3z93hpqQ2Hw4xr7erqKrO3dp53r65mbTAYtOnltN24caPt39hvK7XetM0z7s6dV9vu7na7zPqzWR87y31zTbLGf//Pf7VHjx+3zc3NWneUd5diszXW1tbadHbZhlnt/Py8bW1txY9p/FmqMZOLSXzszw4OD9ra6lr5OhyO2snJcTs+Pm6Dz/7wydzCAGHs8vJygeLexcVF7s3zbB7jgDXKhK2Mvcrf8att7+7Gsd12/PK4ff/99w1ABg1HMSsD/APyMCCtZG7vAfvi/MK0bWN9o20ExK04aMI7t++03Rs75chsNs3aNawNAgh7vvm/b9rnn39eAG1vb+f+qOwQFI7X+Kx/EUDW19fbyupqBejk9DTj5uXPaQIKsPWsPRwM48+0nZ6cBpSTNvjwV/fnG3kRC+aZqIzP4hAfjcbt6OioPpyw4CIyosXAtby7tr6W3y/by5cv2yyTn03OEpGlmgucIodp5r8IS0QNm0ZxZnm83HZ3dtvN/f1i5J1Xbrcbe7ttluAY5x1zABTQhy+P2v/+6U/t6dOnbTXzLgVkzOYU+4xfCwgvEyCMxkJMB9jVfFa/X8ZWgGxubbflMIwfF+eXDWsGH//r+2Eq5yE9LFTPzycFyO7ujdDoZSGHIaurPX0qRc7OOqXzHhAwiuFYA2k0BK702dnZacsrYUfYliCVoSeJyCDGb6xvtjdef6Otray2h989bLcCzP7N/ZoLQ/q8GDculp6cnrS/fPVVO3h+UGwEl5RyYdF5AiU92Qiore2tssFzYPG1QI4dK7FpMBi109OzpONZBX7w4Uf356KP6nKRU9Dykqhy6izOQ3oco4ZLY1OH+rNEZFzoYkSG10UHjOcIZlyECcvLK201c63GaUacnU3yfBr92Gt/9+qr7dat2zXP11/9te0XIHtxaHjNkGhPNG4lwXh53Kn+4OGD9t2jR6Upg+G4xnUAeqpyguaYw2c1jJHC0pU2eT5K+vMNSw8PD9uLoxelKQUIZ+R7MSUTEUiASA8vT8KYcVJgEApayDP0hH5uFQDTOHgZoYSMudaTggwhVMBhMIlFTxEVxfVoxz/8+O/ba6/9KCybtb/8+c8FyCuv3Ko1gFYRzdjj45P25NmzdhqwpfHjCOtYcBJhNlnTGu4JCuZIDT+lUKVW7lu4fAhbBU5a0k020pbB+x/801zkIbaYSO7N84J7RBGq0xg8Xk6OZlJGWmBrK4BlQfloYgbFrhorMuaVv8BaCUuAYFz/hGEZf3PvVnvjjaRM2PTwwYOI61Z75fatjIRtIhqQE5NGFL/48ss2zwL05+DgIPapiF2bjBcArFYcsJ7O0SLCybYJ3biuTmzhl2JgbaAcRZ8Gv/zwX+bDa3QtYKIpwRubZFwU5xSaj5bkJfMGlV4UfH6FGVJOboaKi2hlLg4BEvrW8A+YQDPHLM56vpNqcXP/ZtH65t5+u5HKRZQvYgs2iZxo/vXrr5M2JyWgqFm2XM+Lvdgn+j5Ar9/z/CL2sWE2vehpH3A2rxn8ImxjMzDLqg8++Of5aurxcqLPWAtPJqel6gyF7CzqXFTPpKhZL2YSgulvGoLyRI1GMKT05jpvjWfQPNGSt9Y6T9mdz3rq/TgMUeUePnhYEf7Ra6+VuHN4Etor5+dx9ptvv6nqchy27Aa0aexFn+k0IA+1BgFe5Uo6T69tFXnzxKQ2CbCAopUl9HlWpTY+dHYnZPffv5dWZVCGeNEEp6kSgFmKc671lFVOVgTipLQhUgTJT7nq2eraarHlJFFknMqCZQwwToqoZLwA5OTsvKLz5ptvFku+TEqY86c/+Wm7fft2zSVFUJ1mfJuUevz94wqWMo+rBUbsZ5+A6pWsMQtzrSNVXUsJwiglLuWg2IcRSrX0k1IuNg/u3b87p+Io6qXNjc0qXUqRtIG4+xb0wlX0AI0XJdVPQIoIYyZJLSlEdGuBOGRxmpJfA2aSJb+ICJbsp3q9/vrrBegXX37RJln39q077a233pJVYceTEkrp/Mf/+M/2PL2CLliKBoa4EUYkiHQDSNb1HmAvkyLY4lpKui/no+qpeJo2QaQjxgJX+zD4+bs/m7tRQhmF3ojooD+htBB6EzYOWIjY/nBZOI4uhBZoPkRUW+zCNE2VcfGi5l0INiAFAH2nAfFBGIDCS2nWtNgd6B4ADaBO9zSsAjTGCcxotFRpCgz32Qms7pPWoLMcIFubGrajAk0Zr64578SNstt6g7v3fhEPE7FElxOix6FYU4NQHpIWEf3qTQKcNKvFQ009DHYUaNd4LUQNsFgEcAagMcMXGmM9wNdcCQSjLs5D5Yx59ux5xk7DsPW2t7fXhllDGQcoG4EvpXTafreWymKtCk7AwRBrrK2tpCqut2fpcD2XztbycQGwGH3v/nsJcO9UdaLyz98ML8QymYHuybeVaq5W6h6gLmrDlFxNWmjUAIW2VXViuPekXIGRxTluPmnFUABjpIhf5WduBqDVOLBezj169LgM1twtNE1gqpfJWIHMklXFgFC2Zp3Ly65PbBGQ3ey3UuMC8rNiIWbyT/qxA4PtZwYf/LK37oDoed8bLJEZh2Yc4GTeydXLJk3gqGidqUgpeXISPVUejV1Wq3cX7FDrXdILe86iFRzY2Ox7KGsXq2LH8oq9T8pg5vj22wf1HgO2d7b7filMu0qFSg62eTJxDEzOZW26Zy6pijHWYMPNmzezVUgVTUVUtXTNnrEbiAJabf+/ffbpXOdHJ/Qa6FhKnEkhKPcWk6I2oAitC0M4ATSgAHVRdfQgFlGBRJEBegVj5ftp9iTVMOWZLphWiZSLhrSrQXuRfOcUwa+uOA48TxrpnFGcIHLe76y2m13saDEQS6zJrv2kXFWW3H+epu7Fi6O2l63DZprLsj9jZMDg419/nKCFwhfTND3ZIeYBZkgZ11pKqReAAxj0l5f5s+4BxEeKYI1x0sPfmGVuBtkRLyc9POeksSInOj3HwyDvlvCmvc+cAKdrdGwrO1PvCJ5ddabuqRab9D61a7y2d2l5XOkm4t4x1jEDQPhAm54+fVad9kZSB3vFQq8TQH41h6aOESjKUlWETE5TNjcjWAGknM3kjDOplpjDHNLdGtOd6Nqw2FOY16VlXs58Lg4BhX4UmJlDWTUvW7B0mD2Kgytp6F5nmCoW0c+cwCrwYxPQ6Rf6s3k06kx0PNDH5HlYhlF04uDgMDYcF7swZKFjFbzf/O6TAgSNGUG9e1pQZg1ZUiMGcb6LT+9OOyDqu/OECFgAcZpWgOYlwNUV5LXti7MLwNIeDi0uQDDcPU2cOc9O+45YVI9Cb4BrECstkyLeKTADhhM8mrOzk81m7s9yama97ZyYmdelzD558rSYg/w0ZxKd8dPmT2D1RYPP/v2z2v5DnZIzuPYzoi5Pk4fuKavorFz1zVJ3GkgcYQhHRX5Rrboxyes8805ai7r0HLpEF10yjnOMcjlaMF93KBRPqazeBrUDjDWB7LIPoT9Oz1zTWVqEpGzpQp5VC5Fg6mFs863BL7rld4E1frH2AEM4Mcq5woK29ANLGHqYzhC6crlP1hdhiPHuV7cXQx3aAIdeLAwCBJpjmW5WXos2p1zWUB2U0R6MdIu57707d26X4Q+/+67OK9wrYY5Djg4J6nICBYzNVCtTduaR2PzTPeQmCdD3aPsFHjiCpNMV/OM0g440+VllFyCUJ7bFKE2T2t73B1S7cizOSI1eYXpzJS0wRjqh9sHB89T409qoLYTYc8ZgAIYAtSIcg3SlrsXfFZisTchtLLvozktIn2du4zCqn4X2ThZTNjacnUaf4gD7Y079zh8pBnSfoxwCqaaAd3yxnKMDDFEJe7Djyd17dzNWubJR6pRdGMjYjY21mqDOS6s3Waq9gEhYTB9hMqIFBPW/lzxCi/a9Oohmwl6GGed9KWas9GCkn57RCo0UNk0mF5X35rWObft+egppRR0yZQGFBY45E9JKpwUL+36nM9GGj4+HEVVzbW/v1BxskDZajMG7d3+R7tcmqb8k0iJDMwCF7sBQ7lx6Cq1yHv1w1eYviBIojl3GWT9FU1lDX7vOWTiMKQA/zRaeUT4ugNWpfObQw+ykCevM7c+05ADUo3B2caiTglLg1ulZ3gOq1CTOulC0NF6KK8fE+tnzZ9cHQ72Z5Gel2iCtwtvvvF1aJzepe4+SvCdWNkYLPbGR6+eQnkGVUxznoE8JWNFU6vVOVbnlrL6EoQUYPcGMzIfd9MNa5nc5j9GzSAfP1iOmngHIOkA0j2PKcWzxlcNib+K5cQLrvRL0jMnyPMmzy2rfXxy+iO5sF8OxQ6NYW49/fO/uHBCziAvrINXzMZGJejMKWAym5tBkDIeVOzrCWIaIrMtzFHIv//lBkwDobyV+ehlxi9MFQobZz2iusJMOSIHSncxpNyxlipTXDOKo40Z6h5EYwiYXHzAEm3uZ7hkgiMTzb6maHXBKM/9sJaw5eO/e/ZyYrVTE+zd4yctx/3Kp8r4coBe9a+VsT6UcRsfBjRjVK4k9QxYGWJywZ2E01DVDwFCNxqN8K8j3TMhYQJvPdV4bxbT8K1r53pDpKfo3h6buwRC4Krc61ETX256JRwUnDrpZKZd16I3KZ9xZbAFuBT/gdK1Jn5KUHkUHBz/7+dtzgiha3dnQKoabGCBVMhNR39XYIQ6TtCLnuZ8YRDt84bOe6kDYruq0qmwqAfb1orEnJ4mCrw2uAUEka5qrz5dmLXnMWadvCwBErn+H0iufd9imAtr5BtqMzVxBhB3mKjak63ayLxjmG6eqCDqxxiJ7l1ojNutyoTR45913cupuo9S/+SKmJUZxFJIiSeyOIqyoLL16D0KokteJqisxqb/X1rsjZWFuFkh5TzmWJrb2lzkD7Q70VMEc6ywRcjvYOKb0dhb1U/Y8Lkfpl/uL3fNJhBYgIm1S9PdcKR0GfOP0VFJ7HFHFPABJ9/OAiUUC6gszujP46OMP53LNLlJM9RlVo8MYgyG52CLLVbRzETboTnNMJ1oaNMASLkCZE+uWYwR90CVOE4nhIAdOAUabfJmfDMYeYFdrnqzjPGbSEw6IqtQDBuPtmbzH8YPnz7Oufsi+KB0wfcpz9gEEu9iv2m3v7pTtfYN4lErzsphk47eZ1HcNfv+HT+dYIYKMsieo9jio25dwhEbUFz2JHOGqfL02TDoQMHkuV82xMMiX1r67sVn7/smT3MeQtURoUhss4gpMp/7m1PMAsMT5mhFAcQGGRgmSscDxrA60AwDw0VQK1Yl+xqhqUkhxAKD+BYhYBRTsTudTc0lJKTz49PefzH1vKi+Jn57hKmcRZldG5aLoVPSziHGMcfXvOy6rWbKZ6tvtdKQBoFempZw53KiO1KGMdns8zhFA5j+KUafRFBdnBGU9gGApDQDuympvA4qlmV+6Xs3/tucBfE8NbNJzYCyvYlsY6JedfJEuPYzdzZnIOAXD/4pBAkjCeoIBJIwSoMFvP/11/neIvrk5PDyql4c5uNXSQlfkRYJR3djO6Z4u9jtYM6v8W00UGbEaRxhgjBOqLrzSxZ6FFjgdw6Sc00asAQj02rpfVypgo3uvNr4fVvZVJAHpx5Aq0FKC6aIL5pVqma7ApnV7+zerseT0xpbTuR5QaadBc5+fehH//8r/AwAA//+jOsNnAAATSElEQVRVmVlwZGd1x8/tvVutXRpJo9nNYMuYsYekPMNMnAcTylNFlcMDxQ7GGJxgyAtVSVUq7+TJASqkIO+uVJZKHOIXePeYQnjGAwY89midkVpSa22p1Xv3zf93vulQueN2q+/9lnP+53+270Yvf+sbcbvVtlQqZQf7Feu0O5bJ5qzT61oikdDfWUun09btdiyOY+vpfjKRtKzux/rX7XC/Z13dz2aylkwmLBFF4V63a1zc62lMHEfWbLS0blozuRLaN2nV6rGPz+Wyls1lLNKTdrttHa1dGBjQM+2ZTLqMXa2JrHx3Oi3fc0BjkKOhtavHVUunMtZq8vex9kparVazfD5vA4MFyZawfCHvux9Xqy5XRnLH3diONT566eUXpVfkA1mkLUD0Uwr2zKRYCkHSKUMDlG42mi4cSrbaLX+elFKR/hW0qTB0RVAom81YLpfTOmaNekPLRdq0bu1OgCOdzrqgrRb7trVupPEZH8//arWgEHvxYQxGwjAZGSmrtesaMzIybEODQ1o/aaWNklWPABg5um5MZO7IoIlUwur1uo2OjNhAEaDNegIW4yak57HmRS+8+EIsHYR4z9FEkHanbd2HVscSKAIgPYEEK2ACVuLKZFMW92JrSqmM7nG/UChYJpOS8jWTQcDj/8bXag2t35UwAjuVdgExAhskJXBKn0iTEBIA+ldb66fSgSVYEqD5pKUIrM1kMvqO7ejoSED0pGhPIPT8PixB8Xav7WAiHzIdizkd6TooMLm6mhd99YWvxDxFWQTB0i25UCRLMJj7PaDkesgYQIIVfWQBrIurZdKySMbyon6z2bC9vT0XmjVy+YwsKmpKaFDKZfNaAzc90NiW9umIcdpXazGetRGaMTAo1j1nh+4hFyLBmvGxMZ/DGpVKxQHGBbJye9YCDOTlnkVhDdYJgHV8PIzjHp/oS1/5kmtbr9fQWBSGhk2nGi6Bz8GLvqAAkUqm/LcmKAxELjyuhbJs3tBa+H9HCkJNLpQsFPMBRG0MOwYKoq2e1Wp1B49xKI9RuBCUuIJSUJ59ecRz9uH5yOiI4kVT68RWEyO3d3YUQ9I2Ojrma+GWrOEeIJd0UCUL7CMEwKjgghkxMK0Y8s2XYgJbpXLotCZAHhwcBgs5wgnfnIVasgx0Kw4UPVA1JEgkQBAAn240GpIWuhHwFENklbRYw+UxQpT3mCJFCNb5/ICvty8mlTY2tO6gj8NlAZDgTUDHCF25GUYhnmFd7rNmq930NdNiUk3x4eio6vOGh4elx4Hk6GqPAV8jiuSWWhMZ0RMDHh4d+noZxTs39NdfejGenpmxy5efsjHRD5r/4he/dCoxYEOCNluBMfzOCG2EBYi6LEv0ByxiR0NuwoatVkMgpQyheA6dExqfyaY9a/QU0esCr1gsytYJ29/fd4DZh/nsg7AdsQA25MRaAj4scfAVL8gaPWWfWG4gfN0YyEM2y8htkacp14fhsBU5YAKg8gGQELtgZdMZy5zoy1/9cjyiqPuJTzxrFy9edGXfe+99e3zucU9P87+ct5/9/Gd2eHjoVoGwxAougibBd+Sh4geVA0tKAO3nG46Ojvo4hMea7FMYKLi1t7bKbj2iPjGrTcZSuvS0LkBQBLfos8KzlEDlH9bMChQCaZSKXGHchZTraTVf0L4hFiEA6/DhIo7BsKbYjUxpMQ7AAMsBeeU734qx8I0bN+yTf/ZJzzCvv/5Tm5ubs6kTU3bzrZv2xhtvuH+Sv1mExfuoDwGG5hP8qsrrMpEsqgAmn8Zvi4oh7m6KDePj4+6KGxub7rsNpUMUZC61C/UPa7MeVufy+kVr4tZJAcVv0iixDkASug9zDhVQCf4AgnJpPSNAIW/IWIpN2mNA7g7DG426GwTjkUyIXbA4+stX/sK3fv75P7dnn33Wo/n8r962E5Mn7Nz5c7a8tGyvvvqq5/dTp055JMfioyOjNvf4nE1OTtrqyqrd+fUdd7MxBbNOt+0WYOPBwUHfjJgyNDQki2QcOAIp7ACsbCbnoAAEwiWUPXAZWINwbjl9Axz3YRExhGfUD+wDg7kPM1iTuIN78QyAgmuHBIChuHAVUjXPMDDzos9/8XPxyZMn7cqVK/bcc895gJqff1tFVsGefPJJW1pasu//4PtWOai4C02MjdulS5dsdnbWY86xMso777xj8/PzvjluQjrc2dl2CxBE2ZjNsOhgcVCA9TxuuAU9+FK84WdBeZSBOVgR4WEHwZE1+KAke2BxZ4ie1SQHYDl4rKXLAzLgal3GwzAuWMNF9d0HhM2JKdHnvvDZGCpfvXrVbjx3w3CBmzffcmviNqurq/baa695AL1w4bzNPTbnVkcYBKO4uXX7lv3m17/BOK5wvpBzhlBpgnywSOzzAIVSmnsIQKtAunOpxQ6+eQYb8HWnv56zF3vyISCiHHpTL7W1B0oyNjyXy2gORR5gUDEzPyMmEjsY50zTOozHTf0e83/yzz/WM+Vzlb+XL3/MI39pveS1wfTMtKeuu3fv2kapZDPTM+6PLM7C+CYl/u7err377rvuGlgIX2QMguMCpGPcgRiEhRESoPiQgWADsUHRxC2H1UAXIVkP6zpID78Bos8EwEQhQAlXqIXINCOjw84y9iDmUMHSt1F/4CZc/QINObmi+2urKgKVBkU5BGfxEO1DrkeovIId31yuqJQFWXwWC0HXvd09W71/3+4tLFiptC4g970kZmMiOUELJViHPbwSlWI0ZPwOrAmWpTnr9fQw4OJzApCyrOazN2vxUdb2e5TmsC+A84cSnf35VFWfUHPALGomDNB3QVSjsNSOFt2+cysOmUMWlaJUpz2KICkKbdmcspfaACvLcyUBRZPsqcqvb90DBbVjBclDZZrllRVb0WervGWROiWnrzaEpsfHR1pTrjU0oDplyKtIhEyoMfvg3qI3gcmUehR9XHntg5LBAGojJKMrSb2i2AK7WR8dKBphHcUZF8wikBPXFhcWra2YwZoAURBbKfaYy5whxTZn9E//57+FD9joUiXnQugOqYzbZAWKJYSCXuXNTbv99ttWO6q4a4xpsyHVF+cfecRGxycspzqj1VKw0sZYpLS2YeXtsqdF+h0CJb5N8zd7akYCD0pZ3Cghlu3brphWq8ko3oGr+BODkM4zj+SizQ/Vb+jEQZcMhoyAhkFxZ4QHuKKOBiZOTLqB0IGYNyDgcnJ3AjVNI3UUMlDJRq//13/GkRZj1z6NQiOlBSU47kQv4T6rbNVQoLz9q3k72Nux8YlxrxjpSYYEzLhSdUKpLkHAkxW8N9BGNF1l1R63b91WejwQK2QVAT47O+3FGtaNInXJKuVLGrdd3lWVGfzca41ESgxoudthXeIJ7gpzqV9Yq+9GKE3JTr3B37hmcbAoZh47UBSOwtVZAuOpltG3pzWoo6K33rwZR6IWgwIgISCyIcER3+eiFGdiXc1Qae2+GHIoxVQtKr7QqAFEcWhYB0taSQCmvY9RJSmm0MXubm/bndt31BrsCCilUSk4OjbihVsImOpZkmmPRWtiVasd0mw/VrAH7MXqxDp3VslHecB9+ircoyG3hQXEiab2ABQOmdoKrLgHOhFYqXa7kmtsjGpabNAaMDG6+eabMcUN+ZyYwYagSomruQF5LRRJ0VgoPlhdttL9Vavs72osRRA9guJMTp2sCjahayp9HRBo7IWThKqozV9T0N3a3PD96Xc8lqhwU0hiI+2b98D4YG3dD3lwDT+K0DOvIYR1KNt1Mid5aR1gDq6MS42rRhqQxWERbooxAYv0DhDEP3QL9+SKKCi9uIfefk7yvb//Hob3UzIAIY5QG5CqaJ5YCNqOqTK9duVpJcaeA7K/V/bgytEbqXdweMQ+9OE5y8l9YAg6AhbUIxBykANbEAL2/eED/UPs0gwXjMMmrIxgsAEFW81wRoPgWBOgUYxnfHAZGEB6zXkvo4pWz+mBcCGaSVICNIA1XVXTMMVPzFQ8ctqHnJHKcqlNvGADuYaCHVgeK1YwMbTiXRuVOzxz7eOWFd3X7y9bZbcsgVV0EZhE70nVKE9fva4Aq0pVABKwPDZJWSyNwFCSTSSqK8vfCMGF26CgBzdZm7E+R/O4qDPIUiCMogCNsWBnHxhk5b6DrjGeFQUcTGUOwLMm+/JFiIBdTOK3A/ujH/1TnCC9SgiYATC0584WDW2K2ghdEK0uP3XJClJuc23V9rY3NU4tuVAmE0xMzdjHrz8jQMZMdZ+X50n5fUYfAGFdBOFCgf//Lcor2CGVu48bMoCFkFwo4xZ0fDQOzfkP5TQGS/ulNRgCu2Auz30MaweTMMmPE7RqADfM1P/FkK997cWYAMbJdVbnFSBJYVRQlwr9tKQdqcaYVHmPy0yo+iuXHtj21rqCkg5vNbdWbzpD+oB0EEbLY/WuWCQv9AgvY7qFyAwoARNRGKrjCuztVn0IQqgeg0J9xVEWRbG6X669NtCaKMo36wNWn2Fh7sN7YpX/05i25G/KlZwEcmMq2Ojlb7wcl7d3/VwjJUFoeGCHCyercvZBcDp39qw9/6lP2dTEqG08WLGdrZIKOA5tdHSnyD598rRdvf4nSnHD4p4ykjYmDiwuLSiNlm1T9Yv3LGghYQDDhdc4/eFpHUWwPMricigCWHwjDyMBDr0pFAmk1B2cjeDexBV0gE1eebKewHOW6W9Q6t/n8OrkyWkViIO+Ju7n2es7r3w7pvskB1P0eMeHD2sBSnIaNQQc1dnlZz79aZudPuEusyuXadZ13C/FeP8xe/qsAPlTy+sY8EhAbCnNrq+v+9EgGQWhPBBqhv+nrz4QMCG4Bm4BEAEglAz9Tjixc0sLFocGVKQj8YKKlPjCcxys716wDfSc9QLWu1utCRMAfHxiTM3qY3b27Gmvp5Av+vd/+5eYQ2UuBtFTsGoQRu9hHjZx9CMfu3zZJuUyBNWDHZ146RlVYlWvFgbEjMefuGS7Oo/dV+l8JJBwNxRFYA+A0sCzhHyIeKC7bu2gjIKb7qNUGKOfWFW/wc5dSnM8VuB7ustYpw3Flv6OdD/UUkF+4hJrEJcYyhzSdFhL4wUm6w2phThz+pQ9JnCine3NmPzvi0tA9yMJRsr0jxYFYSzX0blGebNkW4ohZTVw/KYcr8kP9w70PgTraV6kAiunmKQdRVF6IsUHKYNlg18joEsoJaA4dJcTubUBgtTPiys1cLJa3x3cpTSPb54BFev2EwBMA3zmApTXLoKBRjGpt4U+FhZon0huDWPcoH4wbX6+E/3NX383nlaGGFG6XFhYtMXFRdE+79Un965fu25Ly8s6D6nZH//RUzY7M2VbG2t2qIqzoXuU3Zx+HSuwtkTb9+7e0zmngqR6IAClkMI3kTASMJTOoYZQLSLTUcegRE8vkehvKIU6cjHWpTqmtO6/WMqr+Ds8rLi1SQLEEMBsyShFNWekUFKvM0xK1/SWMKc51SqvRWQOtQf8bqimYQyG8vMY/Y13AXz0jz/8h7ipARceecTu3n3f7t2758GQDpHXBBwScV7Ji6dHH71oH/3InK2tLivtlgWI4o4WqWrjhho6qtTFpRUr7+56YKVxootPy5q8dvSyXlaFyqm0sosEojSnc263G2qyBnTuOqrAqGJP7PPOVbGNUzeCIAGWIsvbfjGFVxmxAOFtYFLPAJoMRMCGPRiEt4SVStX29/T+xVLKpjrSfMg+jMS7ZFgO6B5Ulxbuxpxp0isc6dR6ZXnFttVxTkxM2IULH1JbzDuYuj7HrkRVzdm66pD9nW0F4ZB2PfXq4FdS2bu/+z2iKGtB/YQHYxotXKWjFAyd3S3FGQBJyD14o5bNJCVsTkagdtF8jYMle4CruYDS72swAuexvPch8HNYHRo+NZ/0LMo67EkZn0znbHdnT130gcaqhJeMjCW2dSUkaxHDvHiU5NF//OtrMfTp6uaRrLGwsOB/nz173s6eOeMTnfKyiBdXqjAABXaQZYgvoZiStbX5e+9/oB6jrg2yNqED6OvXr7syWLtYLNjU1KStl9ZUGNVln5AGq9WKra2t6Jx1R5ZSWy4g+gfQAzpO0BberbZp4MQUgPKSWwzh4KcrdyBe1Oot29cLN+JTjlJc84Z16D05MSVMFcdMR5UCl7/rYhXlBG1JWWUBJUKK+Pd3f/vdeExNEUrvCEkoB715AfzoxUe9m6SIIgBR/2NNlNkpb6oXaGrOjqOOBSMFrgdKtZyCDau3wUJXnr4itWNtuunp7dy50/b73/1WKfmBz+dQhnU5JymKIRwNQGkOeWi6sCTxi2zHK0viGif5bkSBjHvU1a+0Wz2rHFblIup/5N685MrJ5WklOPqcnJxSoC9KhnMu7+rKA8WWY3eVpaUludSenREBor/69kvKMupucRulVnyRb14r9oT8iBQbEcq8PaOy48Op15qKs6aUQBgsCCCcg5BuQZ81RoZH7YknPurnERsb63b+/Bm965nQwfWyvXPnlrtDLPqyNgfBSjQeaKEvGWlIinNBa15E8YaP1BkACUeBuOJRRYfZokOzoTd1ikkYkyNMAvv0zKz3Wx/cW7DzipPXrj1jJ2dnbWV1TSDsS+687ahmWlle9lrkfwH6cBn/krzo5wAAAABJRU5ErkJggg==

Fork of salesforce/BLIP for a feature-extraction task on 🤗Inference endpoint.

This repository implements a custom task for feature-extraction for 🤗 Inference Endpoints. The code for the customized pipeline is in the pipeline.py. To use deploy this model a an Inference Endpoint you have to select Custom as task to use the pipeline.py file. -> double check if it is selected

expected Request payload

{
  "inputs": "/9j/4AAQSkZJRgABAQEBLAEsAAD/2wBDAAMCAgICAgMC....", // base64 image as bytes
}

below is an example on how to run a request using Python and requests.

Run Request

  1. prepare an image.
!wget https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg

2.run request

import json
from typing import List
import requests as r
import base64
ENDPOINT_URL = "https://api-inference.huggingface.co/models/radames/blip_image_embeddings"
HF_TOKEN = ""
def predict(path_to_image: str = None):
    with open(path_to_image, "rb") as i:
        b64 = base64.b64encode(i.read())
    payload = {"inputs": b64.decode("utf-8")}
    response = r.post(
        ENDPOINT_URL, headers={"X-Wait-For-Model": "true", "Authorization": f"Bearer {HF_TOKEN}"}, json=payload
    )
    return response.json()
prediction = predict(
    path_to_image="palace.jpg"
)

expected output

[0.016450975090265274,
  -0.5551009774208069,
  0.39800673723220825,
  -0.6809228658676147,
  2.053842782974243,
  -0.4712907075881958,...]